© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21581
    Prev
    Next
    INDEX
    Explanations

    -oid -osis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èģĺ
    -0.10
     ere
    -0.08
    .shtml
    -0.08
    yi
    -0.08
     ab
    -0.08
     Tut
    -0.08
    çŀĴ
    -0.08
    åħ·ä½ĵæĥħåĨµ
    -0.07
     Cou
    -0.07
     sit
    -0.07
    POSITIVE LOGITS
    æĦį
    0.10
    éĻ·åħ¥
    0.10
    æĭ¾
    0.10
    æĭįæĭį
    0.10
    å¯Ł
    0.10
    åºŃ
    0.09
    redd
    0.09
    æĢģ
    0.09
    çĪ±åĽ½
    0.09
    ä¸Ńå°ı
    0.09
    Activations Density 0.029%

    No Known Activations